Clover

Offical PyTorch implementation of Clover: Towards A Unified Video-Language Alignment and Fusion Model [arXiv]

Update

(2022-8-18) release pretrain / finetune code and configs

To Do

• [x] Release pretrain code
• [x] Release pretrain config
• [ ] Release pretrain model
• [x] Release finetune code
• [x] Release finetune configs
• [ ] Release finetune model
• [ ] Release installation and usage command

Citation

If you find this work useful in your research, please consider cite:

@article{huang2022clover,
title={Clover: Towards A Unified Video-Language Alignment and Fusion Model},
author={Huang, Jingjia and Li, Yinan and Feng, Jiashi, Xinglong Wu, Sun, Xiaoshuai and Ji, Rongrong},
journal={arXiv preprint arXiv:2207.07885},
year={2022}
}

Acknowledgements

Thanks the contribution of mmaction2 and awesome PyTorch team.